Publisher · GitHub organization

agent-sh

github.com/agent-sh ↗Last audit 12 Oct 2026

agent-sh publishes 31 agent skills on the atlas: 31 SAFE, 0 CAUTION, 0 BLOCK, with a mean score of 89/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “agent-sh: skills and MCP servers”. Retrieved 12 Oct 2026. https://modelsatlas.com/orgs/agent-sh
Listings
31

0 MCP servers · 31 skills

Mean score
89 / 100

mean of the audit scores

Findings
30

across all listings

Stars
31K

on the listed repositories

SAFE 31CAUTION 0BLOCK 0

Everything agent-sh publishes here

Most stars first · stamps show the audited version

Checklistsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Consultagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Debateagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Deslopagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Discover Tasksagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Drift Analysisagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Agent Promptsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Claude Memoryagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Cross Fileagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Docsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Hooksagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Orchestratoragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Pluginsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Promptsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Enhance Skillsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Learnagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Maintain Cross Platformagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Orchestrate Reviewagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Analyzeragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Baseline Manageragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Benchmarkeragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Code Pathsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Investigation Loggeragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Profileragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Theory Gathereragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Perf Theory Testeragent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Repo Intelagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Sync Docsagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Validate Deliveryagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Web Authagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026
Web Browseagent-sh/agentsys
Skill ★ 997
✓SAFEB · 89 · 12 Oct 2026

Questions

Are agent-sh's skills safe to install?
Of 31 listings, 31 are SAFE, 0 CAUTION and 0 BLOCK, with a mean score of 89 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about agent-sh?
It collects every skill and MCP server on the atlas whose source lives under github.com/agent-sh, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.